Community intent report for forum, review, and comparison queries.

Run this report from the CLI, an MCP client, or application code. Every surface uses the same report definition and returns the same evidence. JSON is the source of truth; Markdown makes it readable without hiding dates, limits, warnings, or skipped work.

What this report helps you decide

Which observed search queries suggest that people want opinions, comparisons, or lived experience?

• You need first-party wording to review community or evidence-led content opportunities.
• A repeatable phrase classifier is useful as a starting filter.

Command facts

Report id

community-intent

Execution

Local process

Outputs

JSON and Markdown

Example parameters

site, days, minImpressions, limit

Agent discovery

seo reports describe community-intent --json

Interactive prompts

Human CLI commands only

When this report is not the right tool

These cases need a different report, more evidence, or a human decision. Do not force this report to answer a question its data cannot support.

• You want broader repeated query themes and content gaps, not only searches containing community or comparison wording. Recommended report: Group related search queries. Run query clusters. It groups the returned Search Console demand into repeated themes without requiring the explicit phrase patterns used here.
• You need to decide whether a page should contain first-hand experience, reviews, comparisons, or a discussion format. No automated report can judge whether you have credible experience or which editorial format will satisfy the searcher. Review representative results, the existing page, and the evidence your business can genuinely provide. This report can still select the query wording and current ranking pages for that review.

Data sources and inputs

• Returned Search Console queries. Provides the exact wording, impressions, clicks, and date range behind each match.
• Documented phrase categories. Defines explicit forum, review, comparison, recommendation, and experience patterns.

What this report checks

• Classifies eligible query wording with explicit repeatable phrase rules.
• Ranks matches by returned evidence and keeps ambiguous or unmatched wording outside the result.

How it works

• Classifies query text with documented rules, preserves unmatched rows outside the result, and ranks eligible evidence consistently.

The JSON result keeps dates, thresholds, limits, skipped work, and source completeness beside the finding. Missing, partial, capped, filtered, and complete data remain different states.

Run the report from the CLI

Find returned queries with review, forum, or comparison wording. Agents and CI should inspect the live schema before their first run.

seo community-intent --project example

seo reports describe community-intent --json

seo reports run community-intent --params '{"site":"sc-domain:example.com","days":90,"minImpressions":20,"limit":25}' --json

Project profiles can fill supported property and analytics inputs for the human-facing commands. The catalog form shown here is explicit by design, so agents and CI jobs do not prompt or guess.

How an MCP agent should use it

Call seo_describe_report first so the agent sees when this report is useful and gets the current input schema. Then callseo_run_report with the validated parameters. Read the status, warnings, source limits, and skipped sections before acting on a finding.

{
  "id": "community-intent"
}

{
  "id": "community-intent",
  "params": {
    "site": "sc-domain:example.com",
    "days": 90,
    "minImpressions": 20,
    "limit": 25
  }
}

Use a follow-up report returned by the result instead of guessing the next tool. The local MCP server and CLI use the same report definition and evidence. Their outer transport envelopes differ.

Use the report in a TypeScript app

Install seo as a project dependency, then call the same report catalog used by the CLI and MCP. executeReportrejects an unknown report id or invalid parameters. Provider and runtime failures come back as structured results withisError set.

npm install seo

import { executeReport } from 'seo/mcp'

const result = await executeReport(
  'community-intent',
  {
  "site": "sc-domain:example.com",
  "days": 90,
  "minImpressions": 20,
  "limit": 25
},
)

console.log(result)

The TypeScript library guide also covers direct core functions, schema discovery, and the difference betweenexecuteReport and runReport.

What comes back and how to read it

• Matched queries grouped by phrase category with clicks, impressions, CTR, position, and source dates.
• A limited content review list with caveats for ambiguous wording and anonymised lower-volume queries.
• Read the actual query and current results. The category is a review hypothesis, not a complete intent model.

Start with dataStatus, source details, warnings, and caveats. Then inspect the observed evidence before derived findings or suggested actions.

What this report cannot tell you

• Query wording can be ambiguous, lower-volume queries may be anonymised, and phrase lists cannot capture every expression.

What to do next

1. Decide whether an existing page already answers the need with credible first-hand evidence.
2. Use content optimization for a supported page brief.

Related reports

• Build a content optimization brief. Create a focused brief for one existing page from its own search queries and the content observed on the live URL.
• Group related search queries. Turn a large returned Search Console query set into reproducible groups that are easier to review for shared demand.
• Find opportunities for one page. See which returned search queries are already associated with one URL and what deserves a closer look on the live page.

Sources behind the guidance

These primary sources define the provider data or search controls used in the interpretation above.

• Search Console Search Analytics API guidance

Browse all reports in AI search evidence.